Recommender Systems (RS) became popular tools in many Web services like Netflix, Amazon, or YouTube, because they help a~user to avoid an information overload problem. One of the types of RS are Context-Aware RS (CARS) which exploit contextual information to provide more adequate recommendations. Cross-Domain RS (CDRS) were created as a response to the data sparsity problem which occurs when only few users can provide reviews or ratings for many items. One of the kinds of CDRS are Multi-domain RS which use user information from at least two domains to recommend items from all these domains. In this paper, we investigate how Contextual Ontological User Profile can be used for making multi-domain and context-aware recommendations. We show the improvement of accuracy and diversity of recommendations while combining CARS with CDRS.
Autorzy
Informacje dodatkowe
- DOI
- Cyfrowy identyfikator dokumentu elektronicznego link otwiera się w nowej karcie 10.1007/978-3-030-95408-6_28
- Kategoria
- Aktywność konferencyjna
- Typ
- publikacja w wydawnictwie zbiorowym recenzowanym (także w materiałach konferencyjnych)
- Język
- angielski
- Rok wydania
- 2022
